context-mode 1.0.89 → 1.0.90

package/configs/kilo/AGENTS.md

@@ -1,65 +1,59 @@
 # context-mode — MANDATORY routing rules
 
-You have context-mode MCP tools available. These rules are NOT optional — they protect your context window from flooding. A single unrouted command can dump 56 KB into context and waste the entire session.
+context-mode MCP tools available. Rules protect context window from flooding. One unrouted command dumps 56 KB into context.
 
 ## Think in Code — MANDATORY
 
-When you need to analyze, count, filter, compare, search, parse, transform, or process data: **write code** that does the work via `context-mode_ctx_execute(language, code)` and `console.log()` only the answer. Do NOT read raw data into context to process mentally. Your role is to PROGRAM the analysis, not to COMPUTE it. Write robust, pure JavaScript — no npm dependencies, only Node.js built-ins (`fs`, `path`, `child_process`). Always use `try/catch`, handle `null`/`undefined`, and ensure compatibility with both Node.js and Bun. One script replaces ten tool calls and saves 100x context.
+Analyze/count/filter/compare/search/parse/transform data: **write code** via `context-mode_ctx_execute(language, code)`, `console.log()` only the answer. Do NOT read raw data into context. PROGRAM the analysis, not COMPUTE it. Pure JavaScript — Node.js built-ins only (`fs`, `path`, `child_process`). `try/catch`, handle `null`/`undefined`. One script replaces ten tool calls.
 
-## BLOCKED commands — do NOT attempt these
+## BLOCKED — do NOT attempt
 
 ### curl / wget — BLOCKED
-Any shell command containing `curl` or `wget` will be intercepted and blocked by the context-mode plugin. Do NOT retry.
-Instead use:
-- `context-mode_ctx_fetch_and_index(url, source)` to fetch and index web pages
-- `context-mode_ctx_execute(language: "javascript", code: "const r = await fetch(...)")` to run HTTP calls in sandbox
+Shell `curl`/`wget` intercepted and blocked. Do NOT retry.
+Use: `context-mode_ctx_fetch_and_index(url, source)` or `context-mode_ctx_execute(language: "javascript", code: "const r = await fetch(...)")`
 
 ### Inline HTTP — BLOCKED
-Any shell command containing `fetch('http`, `requests.get(`, `requests.post(`, `http.get(`, or `http.request(` will be intercepted and blocked. Do NOT retry with shell.
-Instead use:
-- `context-mode_ctx_execute(language, code)` to run HTTP calls in sandbox — only stdout enters context
+`fetch('http`, `requests.get(`, `requests.post(`, `http.get(`, `http.request(` — intercepted. Do NOT retry.
+Use: `context-mode_ctx_execute(language, code)` — only stdout enters context
 
 ### Direct web fetching — BLOCKED
-Do NOT use any direct URL fetching tool. Use the sandbox equivalent.
-Instead use:
-- `context-mode_ctx_fetch_and_index(url, source)` then `context-mode_ctx_search(queries)` to query the indexed content
+Use: `context-mode_ctx_fetch_and_index(url, source)` then `context-mode_ctx_search(queries)`
 
-## REDIRECTED tools — use sandbox equivalents
+## REDIRECTED — use sandbox
 
 ### Shell (>20 lines output)
-Shell is ONLY for: `git`, `mkdir`, `rm`, `mv`, `cd`, `ls`, `npm install`, `pip install`, and other short-output commands.
-For everything else, use:
-- `context-mode_ctx_batch_execute(commands, queries)` — run multiple commands + search in ONE call
-- `context-mode_ctx_execute(language: "shell", code: "...")` — run in sandbox, only stdout enters context
+Shell ONLY for: `git`, `mkdir`, `rm`, `mv`, `cd`, `ls`, `npm install`, `pip install`.
+Otherwise: `context-mode_ctx_batch_execute(commands, queries)` or `context-mode_ctx_execute(language: "shell", code: "...")`
 
 ### File reading (for analysis)
-If you are reading a file to **edit** it → reading is correct (edit needs content in context).
-If you are reading to **analyze, explore, or summarize** → use `context-mode_ctx_execute_file(path, language, code)` instead. Only your printed summary enters context.
+Reading to **edit** → reading correct. Reading to **analyze/explore/summarize** → `context-mode_ctx_execute_file(path, language, code)`.
 
 ### grep / search (large results)
-Search results can flood context. Use `context-mode_ctx_execute(language: "shell", code: "grep ...")` to run searches in sandbox. Only your printed summary enters context.
+Use `context-mode_ctx_execute(language: "shell", code: "grep ...")` in sandbox.
 
-## Tool selection hierarchy
+## Tool selection
 
-1. **GATHER**: `context-mode_ctx_batch_execute(commands, queries)` — Primary tool. Runs all commands, auto-indexes output, returns search results. ONE call replaces 30+ individual calls. Each command: `{label: "descriptive header", command: "..."}`. Label becomes FTS5 chunk title — descriptive labels improve search.
-2. **FOLLOW-UP**: `context-mode_ctx_search(queries: ["q1", "q2", ...])` — Query indexed content. Pass ALL questions as array in ONE call.
-3. **PROCESSING**: `context-mode_ctx_execute(language, code)` | `context-mode_ctx_execute_file(path, language, code)` — Sandbox execution. Only stdout enters context.
-4. **WEB**: `context-mode_ctx_fetch_and_index(url, source)` then `context-mode_ctx_search(queries)` — Fetch, chunk, index, query. Raw HTML never enters context.
-5. **INDEX**: `context-mode_ctx_index(content, source)` — Store content in FTS5 knowledge base for later search.
+1. **GATHER**: `context-mode_ctx_batch_execute(commands, queries)` — runs all commands, auto-indexes, returns search. ONE call replaces 30+. Each command: `{label: "header", command: "..."}`.
+2. **FOLLOW-UP**: `context-mode_ctx_search(queries: ["q1", "q2", ...])` — all questions as array, ONE call.
+3. **PROCESSING**: `context-mode_ctx_execute(language, code)` | `context-mode_ctx_execute_file(path, language, code)` — sandbox, only stdout enters context.
+4. **WEB**: `context-mode_ctx_fetch_and_index(url, source)` then `context-mode_ctx_search(queries)` — raw HTML never enters context.
+5. **INDEX**: `context-mode_ctx_index(content, source)` — store in FTS5 for later search.
 
-## Output constraints
+## Output
 
-- Keep responses under 500 words.
-- Write artifacts (code, configs, PRDs) to FILES — never return them as inline text. Return only: file path + 1-line description.
-- When indexing content, use descriptive source labels so others can `search(source: "label")` later.
+Terse like caveman. Technical substance exact. Only fluff die.
+Drop: articles, filler (just/really/basically), pleasantries, hedging. Fragments OK. Short synonyms. Code unchanged.
+Pattern: [thing] [action] [reason]. [next step]. Auto-expand for: security warnings, irreversible actions, user confusion.
+Write artifacts to FILES — never inline. Return: file path + 1-line description.
+Descriptive source labels for `search(source: "label")`.
 
 ## ctx commands
 
 | Command | Action |
 |---------|--------|
-| `ctx stats` | Call the `stats` MCP tool and display the full output verbatim |
-| `ctx doctor` | Call the `doctor` MCP tool, run the returned shell command, display as checklist |
-| `ctx upgrade` | Call the `upgrade` MCP tool, run the returned shell command, display as checklist |
-| `ctx purge` | Call the `purge` MCP tool with confirm: true. Warns before wiping the knowledge base. |
+| `ctx stats` | Call `stats` MCP tool, display full output verbatim |
+| `ctx doctor` | Call `doctor` MCP tool, run returned shell command, display as checklist |
+| `ctx upgrade` | Call `upgrade` MCP tool, run returned shell command, display as checklist |
+| `ctx purge` | Call `purge` MCP tool with confirm: true. Warns before wiping knowledge base. |
 
-After /clear or /compact: knowledge base and session stats are preserved. Use `ctx purge` if you want to start fresh.
+After /clear or /compact: knowledge base and session stats preserved. Use `ctx purge` to start fresh.

package/configs/kiro/KIRO.md

@@ -1,65 +1,59 @@
 # context-mode — MANDATORY routing rules
 
-You have context-mode MCP tools available. These rules are NOT optional — they protect your context window from flooding. A single unrouted command can dump 56 KB into context and waste the entire session.
+context-mode MCP tools available. Rules protect context window from flooding. One unrouted command dumps 56 KB into context.
 
 ## Think in Code — MANDATORY
 
-When you need to analyze, count, filter, compare, search, parse, transform, or process data: **write code** that does the work via `@context-mode/ctx_execute(language, code)` and `console.log()` only the answer. Do NOT read raw data into context to process mentally. Your role is to PROGRAM the analysis, not to COMPUTE it. Write robust, pure JavaScript — no npm dependencies, only Node.js built-ins (`fs`, `path`, `child_process`). Always use `try/catch`, handle `null`/`undefined`, and ensure compatibility with both Node.js and Bun. One script replaces ten tool calls and saves 100x context.
+Analyze/count/filter/compare/search/parse/transform data: **write code** via `@context-mode/ctx_execute(language, code)`, `console.log()` only the answer. Do NOT read raw data into context. PROGRAM the analysis, not COMPUTE it. Pure JavaScript — Node.js built-ins only (`fs`, `path`, `child_process`). `try/catch`, handle `null`/`undefined`. One script replaces ten tool calls.
 
-## BLOCKED commands — do NOT attempt these
+## BLOCKED — do NOT attempt
 
 ### curl / wget — BLOCKED
-Any shell command containing `curl` or `wget` will be intercepted and blocked. Do NOT retry.
-Instead use:
-- `@context-mode/ctx_fetch_and_index(url, source)` to fetch and index web pages
-- `@context-mode/ctx_execute(language: "javascript", code: "const r = await fetch(...)")` to run HTTP calls in sandbox
+Shell `curl`/`wget` intercepted and blocked. Do NOT retry.
+Use: `@context-mode/ctx_fetch_and_index(url, source)` or `@context-mode/ctx_execute(language: "javascript", code: "const r = await fetch(...)")`
 
 ### Inline HTTP — BLOCKED
-Any shell command containing `fetch('http`, `requests.get(`, `requests.post(`, `http.get(`, or `http.request(` will be intercepted and blocked. Do NOT retry with shell.
-Instead use:
-- `@context-mode/ctx_execute(language, code)` to run HTTP calls in sandbox — only stdout enters context
+`fetch('http`, `requests.get(`, `requests.post(`, `http.get(`, `http.request(` — intercepted. Do NOT retry.
+Use: `@context-mode/ctx_execute(language, code)` — only stdout enters context
 
 ### Direct web fetching — BLOCKED
-Direct web fetching is blocked. Use the sandbox equivalent.
-Instead use:
-- `@context-mode/ctx_fetch_and_index(url, source)` then `@context-mode/ctx_search(queries)` to query the indexed content
+Use: `@context-mode/ctx_fetch_and_index(url, source)` then `@context-mode/ctx_search(queries)`
 
-## REDIRECTED tools — use sandbox equivalents
+## REDIRECTED — use sandbox
 
 ### Shell (>20 lines output)
-Shell is ONLY for: `git`, `mkdir`, `rm`, `mv`, `cd`, `ls`, `npm install`, `pip install`, and other short-output commands.
-For everything else, use:
-- `@context-mode/ctx_batch_execute(commands, queries)` — run multiple commands + search in ONE call
-- `@context-mode/ctx_execute(language: "shell", code: "...")` — run in sandbox, only stdout enters context
+Shell ONLY for: `git`, `mkdir`, `rm`, `mv`, `cd`, `ls`, `npm install`, `pip install`.
+Otherwise: `@context-mode/ctx_batch_execute(commands, queries)` or `@context-mode/ctx_execute(language: "shell", code: "...")`
 
 ### fs_read / read (for analysis)
-If you are reading a file to **edit** it → fs_read is correct (edit needs content in context).
-If you are reading to **analyze, explore, or summarize** → use `@context-mode/ctx_execute_file(path, language, code)` instead. Only your printed summary enters context.
+Reading to **edit** → fs_read correct. Reading to **analyze/explore/summarize** → `@context-mode/ctx_execute_file(path, language, code)`.
 
 ### grep / search (large results)
-Search results can flood context. Use `@context-mode/ctx_execute(language: "shell", code: "grep ...")` to run searches in sandbox. Only your printed summary enters context.
+Use `@context-mode/ctx_execute(language: "shell", code: "grep ...")` in sandbox.
 
-## Tool selection hierarchy
+## Tool selection
 
-1. **GATHER**: `@context-mode/ctx_batch_execute(commands, queries)` — Primary tool. Runs all commands, auto-indexes output, returns search results. ONE call replaces 30+ individual calls. Each command: `{label: "descriptive header", command: "..."}`. Label becomes FTS5 chunk title — descriptive labels improve search.
-2. **FOLLOW-UP**: `@context-mode/ctx_search(queries: ["q1", "q2", ...])` — Query indexed content. Pass ALL questions as array in ONE call.
-3. **PROCESSING**: `@context-mode/ctx_execute(language, code)` | `@context-mode/ctx_execute_file(path, language, code)` — Sandbox execution. Only stdout enters context.
-4. **WEB**: `@context-mode/ctx_fetch_and_index(url, source)` then `@context-mode/ctx_search(queries)` — Fetch, chunk, index, query. Raw HTML never enters context.
-5. **INDEX**: `@context-mode/ctx_index(content, source)` — Store content in FTS5 knowledge base for later search.
+1. **GATHER**: `@context-mode/ctx_batch_execute(commands, queries)` — runs all commands, auto-indexes, returns search. ONE call replaces 30+. Each command: `{label: "header", command: "..."}`.
+2. **FOLLOW-UP**: `@context-mode/ctx_search(queries: ["q1", "q2", ...])` — all questions as array, ONE call.
+3. **PROCESSING**: `@context-mode/ctx_execute(language, code)` | `@context-mode/ctx_execute_file(path, language, code)` — sandbox, only stdout enters context.
+4. **WEB**: `@context-mode/ctx_fetch_and_index(url, source)` then `@context-mode/ctx_search(queries)` — raw HTML never enters context.
+5. **INDEX**: `@context-mode/ctx_index(content, source)` — store in FTS5 for later search.
 
-## Output constraints
+## Output
 
-- Keep responses under 500 words.
-- Write artifacts (code, configs, PRDs) to FILES — never return them as inline text. Return only: file path + 1-line description.
-- When indexing content, use descriptive source labels so others can `search(source: "label")` later.
+Terse like caveman. Technical substance exact. Only fluff die.
+Drop: articles, filler (just/really/basically), pleasantries, hedging. Fragments OK. Short synonyms. Code unchanged.
+Pattern: [thing] [action] [reason]. [next step]. Auto-expand for: security warnings, irreversible actions, user confusion.
+Write artifacts to FILES — never inline. Return: file path + 1-line description.
+Descriptive source labels for `search(source: "label")`.
 
 ## ctx commands
 
 | Command | Action |
 |---------|--------|
-| `ctx stats` | Call the `stats` MCP tool and display the full output verbatim |
-| `ctx doctor` | Call the `doctor` MCP tool, run the returned shell command, display as checklist |
-| `ctx upgrade` | Call the `upgrade` MCP tool, run the returned shell command, display as checklist |
-| `ctx purge` | Call the `purge` MCP tool with confirm: true. Warns before wiping the knowledge base. |
+| `ctx stats` | Call `stats` MCP tool, display full output verbatim |
+| `ctx doctor` | Call `doctor` MCP tool, run returned shell command, display as checklist |
+| `ctx upgrade` | Call `upgrade` MCP tool, run returned shell command, display as checklist |
+| `ctx purge` | Call `purge` MCP tool with confirm: true. Warns before wiping knowledge base. |
 
-After /clear or /compact: knowledge base and session stats are preserved. Use `ctx purge` if you want to start fresh.
+After /clear or /compact: knowledge base and session stats preserved. Use `ctx purge` to start fresh.

package/configs/kiro/agent.json

@@ -4,7 +4,7 @@
   "hooks": {
     "preToolUse": [
       {
-        "matcher": "*",
+        "matcher": "execute_bash|fs_read|@context-mode/ctx_execute|@context-mode/ctx_execute_file|@context-mode/ctx_batch_execute",
         "command": "context-mode hook kiro pretooluse"
       }
     ],

package/configs/openclaw/AGENTS.md

@@ -1,65 +1,59 @@
 # context-mode — MANDATORY routing rules
 
-You have context-mode MCP tools available. These rules are NOT optional — they protect your context window from flooding. A single unrouted command can dump 56 KB into context and waste the entire session.
+context-mode MCP tools available. Rules protect context window from flooding. One unrouted command dumps 56 KB into context.
 
 ## Think in Code — MANDATORY
 
-When you need to analyze, count, filter, compare, search, parse, transform, or process data: **write code** that does the work via `ctx_execute(language, code)` and `console.log()` only the answer. Do NOT read raw data into context to process mentally. Your role is to PROGRAM the analysis, not to COMPUTE it. Write robust, pure JavaScript — no npm dependencies, only Node.js built-ins (`fs`, `path`, `child_process`). Always use `try/catch`, handle `null`/`undefined`, and ensure compatibility with both Node.js and Bun. One script replaces ten tool calls and saves 100x context.
+Analyze/count/filter/compare/search/parse/transform data: **write code** via `context-mode__ctx_execute(language, code)`, `console.log()` only the answer. Do NOT read raw data into context. PROGRAM the analysis, not COMPUTE it. Pure JavaScript — Node.js built-ins only (`fs`, `path`, `child_process`). `try/catch`, handle `null`/`undefined`. One script replaces ten tool calls.
 
-## BLOCKED commands — do NOT attempt these
+## BLOCKED — do NOT attempt
 
 ### curl / wget — BLOCKED
-Any shell command containing `curl` or `wget` will be intercepted and blocked by the context-mode plugin. Do NOT retry.
-Instead use:
-- `ctx_fetch_and_index(url, source)` to fetch and index web pages
-- `ctx_execute(language: "javascript", code: "const r = await fetch(...)")` to run HTTP calls in sandbox
+Shell `curl`/`wget` intercepted and blocked. Do NOT retry.
+Use: `context-mode__ctx_fetch_and_index(url, source)` or `context-mode__ctx_execute(language: "javascript", code: "const r = await fetch(...)")`
 
 ### Inline HTTP — BLOCKED
-Any shell command containing `fetch('http`, `requests.get(`, `requests.post(`, `http.get(`, or `http.request(` will be intercepted and blocked. Do NOT retry with shell.
-Instead use:
-- `ctx_execute(language, code)` to run HTTP calls in sandbox — only stdout enters context
+`fetch('http`, `requests.get(`, `requests.post(`, `http.get(`, `http.request(` — intercepted. Do NOT retry.
+Use: `context-mode__ctx_execute(language, code)` — only stdout enters context
 
 ### Direct web fetching — BLOCKED
-Do NOT use any direct URL fetching tool. Use the sandbox equivalent.
-Instead use:
-- `ctx_fetch_and_index(url, source)` then `ctx_search(queries)` to query the indexed content
+Use: `context-mode__ctx_fetch_and_index(url, source)` then `context-mode__ctx_search(queries)`
 
-## REDIRECTED tools — use sandbox equivalents
+## REDIRECTED — use sandbox
 
 ### Shell (>20 lines output)
-Shell is ONLY for: `git`, `mkdir`, `rm`, `mv`, `cd`, `ls`, `npm install`, `pip install`, and other short-output commands.
-For everything else, use:
-- `ctx_batch_execute(commands, queries)` — run multiple commands + search in ONE call
-- `ctx_execute(language: "shell", code: "...")` — run in sandbox, only stdout enters context
+Shell ONLY for: `git`, `mkdir`, `rm`, `mv`, `cd`, `ls`, `npm install`, `pip install`.
+Otherwise: `context-mode__ctx_batch_execute(commands, queries)` or `context-mode__ctx_execute(language: "shell", code: "...")`
 
 ### File reading (for analysis)
-If you are reading a file to **edit** it → reading is correct (edit needs content in context).
-If you are reading to **analyze, explore, or summarize** → use `ctx_execute_file(path, language, code)` instead. Only your printed summary enters context.
+Reading to **edit** → reading correct. Reading to **analyze/explore/summarize** → `context-mode__ctx_execute_file(path, language, code)`.
 
 ### grep / search (large results)
-Search results can flood context. Use `ctx_execute(language: "shell", code: "grep ...")` to run searches in sandbox. Only your printed summary enters context.
+Use `context-mode__ctx_execute(language: "shell", code: "grep ...")` in sandbox.
 
-## Tool selection hierarchy
+## Tool selection
 
-1. **GATHER**: `ctx_batch_execute(commands, queries)` — Primary tool. Runs all commands, auto-indexes output, returns search results. ONE call replaces 30+ individual calls. Each command: `{label: "descriptive header", command: "..."}`. Label becomes FTS5 chunk title — descriptive labels improve search.
-2. **FOLLOW-UP**: `ctx_search(queries: ["q1", "q2", ...])` — Query indexed content. Pass ALL questions as array in ONE call.
-3. **PROCESSING**: `ctx_execute(language, code)` | `ctx_execute_file(path, language, code)` — Sandbox execution. Only stdout enters context.
-4. **WEB**: `ctx_fetch_and_index(url, source)` then `ctx_search(queries)` — Fetch, chunk, index, query. Raw HTML never enters context.
-5. **INDEX**: `ctx_index(content, source)` — Store content in FTS5 knowledge base for later search.
+1. **GATHER**: `context-mode__ctx_batch_execute(commands, queries)` — runs all commands, auto-indexes, returns search. ONE call replaces 30+. Each command: `{label: "header", command: "..."}`.
+2. **FOLLOW-UP**: `context-mode__ctx_search(queries: ["q1", "q2", ...])` — all questions as array, ONE call.
+3. **PROCESSING**: `context-mode__ctx_execute(language, code)` | `context-mode__ctx_execute_file(path, language, code)` — sandbox, only stdout enters context.
+4. **WEB**: `context-mode__ctx_fetch_and_index(url, source)` then `context-mode__ctx_search(queries)` — raw HTML never enters context.
+5. **INDEX**: `context-mode__ctx_index(content, source)` — store in FTS5 for later search.
 
-## Output constraints
+## Output
 
-- Keep responses under 500 words.
-- Write artifacts (code, configs, PRDs) to FILES — never return them as inline text. Return only: file path + 1-line description.
-- When indexing content, use descriptive source labels so others can `search(source: "label")` later.
+Terse like caveman. Technical substance exact. Only fluff die.
+Drop: articles, filler (just/really/basically), pleasantries, hedging. Fragments OK. Short synonyms. Code unchanged.
+Pattern: [thing] [action] [reason]. [next step]. Auto-expand for: security warnings, irreversible actions, user confusion.
+Write artifacts to FILES — never inline. Return: file path + 1-line description.
+Descriptive source labels for `search(source: "label")`.
 
 ## ctx commands
 
 | Command | Action |
 |---------|--------|
-| `ctx stats` | Call the `stats` MCP tool and display the full output verbatim |
-| `ctx doctor` | Call the `doctor` MCP tool, run the returned shell command, display as checklist |
-| `ctx upgrade` | Call the `upgrade` MCP tool, run the returned shell command, display as checklist |
-| `ctx purge` | Call the `purge` MCP tool with confirm: true. Warns before wiping the knowledge base. |
+| `ctx stats` | Call `stats` MCP tool, display full output verbatim |
+| `ctx doctor` | Call `doctor` MCP tool, run returned shell command, display as checklist |
+| `ctx upgrade` | Call `upgrade` MCP tool, run returned shell command, display as checklist |
+| `ctx purge` | Call `purge` MCP tool with confirm: true. Warns before wiping knowledge base. |
 
-After /clear or /compact: knowledge base and session stats are preserved. Use `ctx purge` if you want to start fresh.
+After /clear or /compact: knowledge base and session stats preserved. Use `ctx purge` to start fresh.

package/configs/opencode/AGENTS.md

@@ -1,65 +1,59 @@
 # context-mode — MANDATORY routing rules
 
-You have context-mode MCP tools available. These rules are NOT optional — they protect your context window from flooding. A single unrouted command can dump 56 KB into context and waste the entire session.
+context-mode MCP tools available. Rules protect context window from flooding. One unrouted command dumps 56 KB into context.
 
 ## Think in Code — MANDATORY
 
-When you need to analyze, count, filter, compare, search, parse, transform, or process data: **write code** that does the work via `context-mode_ctx_execute(language, code)` and `console.log()` only the answer. Do NOT read raw data into context to process mentally. Your role is to PROGRAM the analysis, not to COMPUTE it. Write robust, pure JavaScript — no npm dependencies, only Node.js built-ins (`fs`, `path`, `child_process`). Always use `try/catch`, handle `null`/`undefined`, and ensure compatibility with both Node.js and Bun. One script replaces ten tool calls and saves 100x context.
+Analyze/count/filter/compare/search/parse/transform data: **write code** via `context-mode_ctx_execute(language, code)`, `console.log()` only the answer. Do NOT read raw data into context. PROGRAM the analysis, not COMPUTE it. Pure JavaScript — Node.js built-ins only (`fs`, `path`, `child_process`). `try/catch`, handle `null`/`undefined`. One script replaces ten tool calls.
 
-## BLOCKED commands — do NOT attempt these
+## BLOCKED — do NOT attempt
 
 ### curl / wget — BLOCKED
-Any shell command containing `curl` or `wget` will be intercepted and blocked by the context-mode plugin. Do NOT retry.
-Instead use:
-- `context-mode_ctx_fetch_and_index(url, source)` to fetch and index web pages
-- `context-mode_ctx_execute(language: "javascript", code: "const r = await fetch(...)")` to run HTTP calls in sandbox
+Shell `curl`/`wget` intercepted and blocked. Do NOT retry.
+Use: `context-mode_ctx_fetch_and_index(url, source)` or `context-mode_ctx_execute(language: "javascript", code: "const r = await fetch(...)")`
 
 ### Inline HTTP — BLOCKED
-Any shell command containing `fetch('http`, `requests.get(`, `requests.post(`, `http.get(`, or `http.request(` will be intercepted and blocked. Do NOT retry with shell.
-Instead use:
-- `context-mode_ctx_execute(language, code)` to run HTTP calls in sandbox — only stdout enters context
+`fetch('http`, `requests.get(`, `requests.post(`, `http.get(`, `http.request(` — intercepted. Do NOT retry.
+Use: `context-mode_ctx_execute(language, code)` — only stdout enters context
 
 ### Direct web fetching — BLOCKED
-Do NOT use any direct URL fetching tool. Use the sandbox equivalent.
-Instead use:
-- `context-mode_ctx_fetch_and_index(url, source)` then `context-mode_ctx_search(queries)` to query the indexed content
+Use: `context-mode_ctx_fetch_and_index(url, source)` then `context-mode_ctx_search(queries)`
 
-## REDIRECTED tools — use sandbox equivalents
+## REDIRECTED — use sandbox
 
 ### Shell (>20 lines output)
-Shell is ONLY for: `git`, `mkdir`, `rm`, `mv`, `cd`, `ls`, `npm install`, `pip install`, and other short-output commands.
-For everything else, use:
-- `context-mode_ctx_batch_execute(commands, queries)` — run multiple commands + search in ONE call
-- `context-mode_ctx_execute(language: "shell", code: "...")` — run in sandbox, only stdout enters context
+Shell ONLY for: `git`, `mkdir`, `rm`, `mv`, `cd`, `ls`, `npm install`, `pip install`.
+Otherwise: `context-mode_ctx_batch_execute(commands, queries)` or `context-mode_ctx_execute(language: "shell", code: "...")`
 
 ### File reading (for analysis)
-If you are reading a file to **edit** it → reading is correct (edit needs content in context).
-If you are reading to **analyze, explore, or summarize** → use `context-mode_ctx_execute_file(path, language, code)` instead. Only your printed summary enters context.
+Reading to **edit** → reading correct. Reading to **analyze/explore/summarize** → `context-mode_ctx_execute_file(path, language, code)`.
 
 ### grep / search (large results)
-Search results can flood context. Use `context-mode_ctx_execute(language: "shell", code: "grep ...")` to run searches in sandbox. Only your printed summary enters context.
+Use `context-mode_ctx_execute(language: "shell", code: "grep ...")` in sandbox.
 
-## Tool selection hierarchy
+## Tool selection
 
-1. **GATHER**: `context-mode_ctx_batch_execute(commands, queries)` — Primary tool. Runs all commands, auto-indexes output, returns search results. ONE call replaces 30+ individual calls. Each command: `{label: "descriptive header", command: "..."}`. Label becomes FTS5 chunk title — descriptive labels improve search.
-2. **FOLLOW-UP**: `context-mode_ctx_search(queries: ["q1", "q2", ...])` — Query indexed content. Pass ALL questions as array in ONE call.
-3. **PROCESSING**: `context-mode_ctx_execute(language, code)` | `context-mode_ctx_execute_file(path, language, code)` — Sandbox execution. Only stdout enters context.
-4. **WEB**: `context-mode_ctx_fetch_and_index(url, source)` then `context-mode_ctx_search(queries)` — Fetch, chunk, index, query. Raw HTML never enters context.
-5. **INDEX**: `context-mode_ctx_index(content, source)` — Store content in FTS5 knowledge base for later search.
+1. **GATHER**: `context-mode_ctx_batch_execute(commands, queries)` — runs all commands, auto-indexes, returns search. ONE call replaces 30+. Each command: `{label: "header", command: "..."}`.
+2. **FOLLOW-UP**: `context-mode_ctx_search(queries: ["q1", "q2", ...])` — all questions as array, ONE call.
+3. **PROCESSING**: `context-mode_ctx_execute(language, code)` | `context-mode_ctx_execute_file(path, language, code)` — sandbox, only stdout enters context.
+4. **WEB**: `context-mode_ctx_fetch_and_index(url, source)` then `context-mode_ctx_search(queries)` — raw HTML never enters context.
+5. **INDEX**: `context-mode_ctx_index(content, source)` — store in FTS5 for later search.
 
-## Output constraints
+## Output
 
-- Keep responses under 500 words.
-- Write artifacts (code, configs, PRDs) to FILES — never return them as inline text. Return only: file path + 1-line description.
-- When indexing content, use descriptive source labels so others can `search(source: "label")` later.
+Terse like caveman. Technical substance exact. Only fluff die.
+Drop: articles, filler (just/really/basically), pleasantries, hedging. Fragments OK. Short synonyms. Code unchanged.
+Pattern: [thing] [action] [reason]. [next step]. Auto-expand for: security warnings, irreversible actions, user confusion.
+Write artifacts to FILES — never inline. Return: file path + 1-line description.
+Descriptive source labels for `search(source: "label")`.
 
 ## ctx commands
 
 | Command | Action |
 |---------|--------|
-| `ctx stats` | Call the `stats` MCP tool and display the full output verbatim |
-| `ctx doctor` | Call the `doctor` MCP tool, run the returned shell command, display as checklist |
-| `ctx upgrade` | Call the `upgrade` MCP tool, run the returned shell command, display as checklist |
-| `ctx purge` | Call the `purge` MCP tool with confirm: true. Warns before wiping the knowledge base. |
+| `ctx stats` | Call `stats` MCP tool, display full output verbatim |
+| `ctx doctor` | Call `doctor` MCP tool, run returned shell command, display as checklist |
+| `ctx upgrade` | Call `upgrade` MCP tool, run returned shell command, display as checklist |
+| `ctx purge` | Call `purge` MCP tool with confirm: true. Warns before wiping knowledge base. |
 
-After /clear or /compact: knowledge base and session stats are preserved. Use `ctx purge` if you want to start fresh.
+After /clear or /compact: knowledge base and session stats preserved. Use `ctx purge` to start fresh.

package/configs/pi/AGENTS.md

@@ -1,65 +1,60 @@
 # context-mode — MANDATORY routing rules
 
-You have context-mode MCP tools available. These rules are NOT optional — they protect your context window from flooding. A single unrouted command can dump 56 KB into context and waste the entire session. Pi enforces routing via hooks (`tool_call` blocks `curl`/`wget`) AND these instructions. Hooks provide hard enforcement at the tool level; these rules provide completeness — covering redirections and patterns that hooks alone cannot catch. Follow them strictly.
+context-mode MCP tools available. Rules protect context window from flooding. One unrouted command dumps 56 KB into context. Pi enforces routing via hooks (`tool_call` blocks `curl`/`wget`) AND these instructions. Hooks = hard enforcement; rules = completeness for redirections hooks cannot catch.
 
 ## Think in Code — MANDATORY
 
-When you need to analyze, count, filter, compare, search, parse, transform, or process data: **write code** that does the work via `ctx_execute(language, code)` and `console.log()` only the answer. Do NOT read raw data into context to process mentally. Your role is to PROGRAM the analysis, not to COMPUTE it. Write robust, pure JavaScript — no npm dependencies, only Node.js built-ins (`fs`, `path`, `child_process`). Always use `try/catch`, handle `null`/`undefined`, and ensure compatibility with both Node.js and Bun. One script replaces ten tool calls and saves 100x context.
+Analyze/count/filter/compare/search/parse/transform data: **write code** via `ctx_execute(language, code)`, `console.log()` only the answer. Do NOT read raw data into context. PROGRAM the analysis, not COMPUTE it. Pure JavaScript — Node.js built-ins only (`fs`, `path`, `child_process`). `try/catch`, handle `null`/`undefined`. One script replaces ten tool calls.
 
-## BLOCKED commands — do NOT use these
+## BLOCKED — do NOT use
 
 ### curl / wget — FORBIDDEN (hook-enforced)
-Do NOT use `curl` or `wget` in any `bash` command. Pi's `tool_call` hooks block these at the tool level. Even if they weren't blocked, they dump raw HTTP responses directly into your context window.
-Instead use:
-- `ctx_fetch_and_index(url, source)` to fetch and index web pages
-- `ctx_execute(language: "javascript", code: "const r = await fetch(...)")` to run HTTP calls in sandbox
+Do NOT use `curl`/`wget` in `bash`. Pi hooks block these. Dumps raw HTTP into context.
+Use: `ctx_fetch_and_index(url, source)` or `ctx_execute(language: "javascript", code: "const r = await fetch(...)")`
 
 ### Inline HTTP — FORBIDDEN
-Do NOT run inline HTTP calls via `node -e "fetch(..."`, `python -c "requests.get(..."`, or similar patterns. They bypass the sandbox and flood context.
-Instead use:
-- `ctx_execute(language, code)` to run HTTP calls in sandbox — only stdout enters context
+No `node -e "fetch(..."`, `python -c "requests.get(..."`. Bypasses sandbox.
+Use: `ctx_execute(language, code)` — only stdout enters context
 
 ### Direct web fetching — FORBIDDEN
-Do NOT use any direct URL fetching tool. Raw HTML can exceed 100 KB.
-Instead use:
-- `ctx_fetch_and_index(url, source)` then `ctx_search(queries)` to query the indexed content
+Raw HTML can exceed 100 KB.
+Use: `ctx_fetch_and_index(url, source)` then `ctx_search(queries)`
 
-## REDIRECTED tools — use sandbox equivalents
+## REDIRECTED — use sandbox
 
 ### bash (>20 lines output)
-`bash` is ONLY for: `git`, `mkdir`, `rm`, `mv`, `cd`, `ls`, `npm install`, `pip install`, and other short-output commands.
-For everything else, use:
-- `ctx_batch_execute(commands, queries)` — run multiple commands + search in ONE call
-- `ctx_execute(language: "shell", code: "...")` — run in sandbox, only stdout enters context
+`bash` ONLY for: `git`, `mkdir`, `rm`, `mv`, `cd`, `ls`, `npm install`, `pip install`.
+Otherwise: `ctx_batch_execute(commands, queries)` or `ctx_execute(language: "shell", code: "...")`
 
 ### read (for analysis)
-If you are reading a file to **edit** it → `read` is correct (edit needs content in context).
-If you are reading to **analyze, explore, or summarize** → use `ctx_execute_file(path, language, code)` instead. Only your printed summary enters context. The raw file stays in the sandbox.
+Reading to **edit** → `read` correct. Reading to **analyze/explore/summarize** → `ctx_execute_file(path, language, code)`.
 
 ### grep / find (large results)
-Search results from `grep` or `find` can flood context. Use `ctx_execute(language: "shell", code: "grep ...")` to run searches in sandbox. Only your printed summary enters context.
+Use `ctx_execute(language: "shell", code: "grep ...")` in sandbox.
 
-## Tool selection hierarchy
+## Tool selection
 
-1. **GATHER**: `ctx_batch_execute(commands, queries)` — Primary tool. Runs all commands, auto-indexes output, returns search results. ONE call replaces 30+ individual calls. Each command: `{label: "descriptive header", command: "..."}`. Label becomes FTS5 chunk title — descriptive labels improve search.
-2. **FOLLOW-UP**: `ctx_search(queries: ["q1", "q2", ...])` — Query indexed content. Pass ALL questions as array in ONE call.
-3. **PROCESSING**: `ctx_execute(language, code)` | `ctx_execute_file(path, language, code)` — Sandbox execution. Only stdout enters context.
-4. **WEB**: `ctx_fetch_and_index(url, source)` then `ctx_search(queries)` — Fetch, chunk, index, query. Raw HTML never enters context.
-5. **INDEX**: `ctx_index(content, source)` — Store content in FTS5 knowledge base for later search.
+1. **GATHER**: `ctx_batch_execute(commands, queries)` — runs all commands, auto-indexes, returns search. ONE call replaces 30+. Each command: `{label: "header", command: "..."}`.
+2. **FOLLOW-UP**: `ctx_search(queries: ["q1", "q2", ...])` — all questions as array, ONE call.
+3. **PROCESSING**: `ctx_execute(language, code)` | `ctx_execute_file(path, language, code)` — sandbox, only stdout enters context.
+4. **WEB**: `ctx_fetch_and_index(url, source)` then `ctx_search(queries)` — raw HTML never enters context.
+5. **INDEX**: `ctx_index(content, source)` — store in FTS5 for later search.
 
-## Output constraints
+## Output
 
-- Keep responses under 500 words.
-- Write artifacts (code, configs, PRDs) to FILES — never return them as inline text. Return only: file path + 1-line description.
-- When indexing content, use descriptive source labels so others can `search(source: "label")` later.
+Terse like caveman. Technical substance exact. Only fluff die.
+Drop: articles, filler (just/really/basically), pleasantries, hedging. Fragments OK. Short synonyms. Code unchanged.
+Pattern: [thing] [action] [reason]. [next step]. Auto-expand for: security warnings, irreversible actions, user confusion.
+Write artifacts to FILES — never inline. Return: file path + 1-line description.
+Descriptive source labels for `search(source: "label")`.
 
 ## ctx commands
 
 | Command | Action |
 |---------|--------|
-| `ctx stats` | Call the `stats` MCP tool and display the full output verbatim |
-| `ctx doctor` | Call the `doctor` MCP tool, run the returned shell command, display as checklist |
-| `ctx upgrade` | Call the `upgrade` MCP tool, run the returned shell command, display as checklist |
-| `ctx purge` | Call the `purge` MCP tool with confirm: true. Warns before wiping the knowledge base. |
+| `ctx stats` | Call `stats` MCP tool, display full output verbatim |
+| `ctx doctor` | Call `doctor` MCP tool, run returned shell command, display as checklist |
+| `ctx upgrade` | Call `upgrade` MCP tool, run returned shell command, display as checklist |
+| `ctx purge` | Call `purge` MCP tool with confirm: true. Warns before wiping knowledge base. |
 
-After /clear or /compact: knowledge base and session stats are preserved. Use `ctx purge` if you want to start fresh.
+After /clear or /compact: knowledge base and session stats preserved. Use `ctx purge` to start fresh.

package/configs/qwen-code/QWEN.md

@@ -0,0 +1,63 @@
+# context-mode — MANDATORY routing rules
+
+context-mode MCP tools available. Rules protect context window from flooding. One unrouted command dumps 56 KB into context.
+
+## Think in Code — MANDATORY
+
+Analyze/count/filter/compare/search/parse/transform data: **write code** via `ctx_execute(language, code)`, `console.log()` only the answer. Do NOT read raw data into context. PROGRAM the analysis, not COMPUTE it. Pure JavaScript — Node.js built-ins only (`fs`, `path`, `child_process`). `try/catch`, handle `null`/`undefined`. One script replaces ten tool calls.
+
+## BLOCKED — do NOT attempt
+
+### curl / wget — BLOCKED
+Bash `curl`/`wget` intercepted and replaced with error. Do NOT retry.
+Use: `ctx_fetch_and_index(url, source)` or `ctx_execute(language: "javascript", code: "const r = await fetch(...)")`
+
+### Inline HTTP — BLOCKED
+`fetch('http`, `requests.get(`, `requests.post(`, `http.get(`, `http.request(` — intercepted. Do NOT retry.
+Use: `ctx_execute(language, code)` — only stdout enters context
+
+### WebFetch — BLOCKED
+Use: `ctx_fetch_and_index(url, source)` then `ctx_search(queries)`
+
+## REDIRECTED — use sandbox
+
+### Bash (>20 lines output)
+Bash ONLY for: `git`, `mkdir`, `rm`, `mv`, `cd`, `ls`, `npm install`, `pip install`.
+Otherwise: `ctx_batch_execute(commands, queries)` or `ctx_execute(language: "shell", code: "...")`
+
+### Read (for analysis)
+Reading to **Edit** → Read correct. Reading to **analyze/explore/summarize** → `ctx_execute_file(path, language, code)`.
+
+### Grep (large results)
+Use `ctx_execute(language: "shell", code: "grep ...")` in sandbox.
+
+## Tool selection
+
+1. **GATHER**: `ctx_batch_execute(commands, queries)` — runs all commands, auto-indexes, returns search. ONE call replaces 30+. Each command: `{label: "header", command: "..."}`.
+2. **FOLLOW-UP**: `ctx_search(queries: ["q1", "q2", ...])` — all questions as array, ONE call.
+3. **PROCESSING**: `ctx_execute(language, code)` | `ctx_execute_file(path, language, code)` — sandbox, only stdout enters context.
+4. **WEB**: `ctx_fetch_and_index(url, source)` then `ctx_search(queries)` — raw HTML never enters context.
+5. **INDEX**: `ctx_index(content, source)` — store in FTS5 for later search.
+
+## Subagent routing
+
+Routing block auto-injected into subagent prompts. Bash-type subagents upgraded to general-purpose. No manual instruction needed.
+
+## Output
+
+Terse like caveman. Technical substance exact. Only fluff die.
+Drop: articles, filler (just/really/basically), pleasantries, hedging. Fragments OK. Short synonyms. Code unchanged.
+Pattern: [thing] [action] [reason]. [next step]. Auto-expand for: security warnings, irreversible actions, user confusion.
+Write artifacts to FILES — never inline. Return: file path + 1-line description.
+Descriptive source labels for `ctx_search(source: "label")`.
+
+## ctx commands
+
+| Command | Action |
+|---------|--------|
+| `ctx stats` | Call `ctx_stats` MCP tool, display full output verbatim |
+| `ctx doctor` | Call `ctx_doctor` MCP tool, run returned shell command, display as checklist |
+| `ctx upgrade` | Call `ctx_upgrade` MCP tool, run returned shell command, display as checklist |
+| `ctx purge` | Call `ctx_purge` MCP tool with confirm: true. Warns before wiping knowledge base. |
+
+After /clear or /compact: knowledge base and session stats preserved. Use `ctx purge` to start fresh.